Sakhanda Wire
NVDA $153.77 -1.52% MSFT $504.91 -2.53% GOOGL $281.52 -0.78% META $620.99 -0.87% AMZN $256.80 -0.37%
← Back to the news

Google introduces two Gemini 3.8 Flash TTS models

Google has launched Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two speech-generation models designed for different production needs. Flash TTS is aimed at interactive entertainment, game development and long-form narration, while Flash-Lite TTS targets automated dubbing, conversational agents and large-scale translation workflows.

The models replace a fixed set of 30 legacy voices with more than 2,000 vocal profiles covering regional varieties across over 100 languages. Google also plans a text-controlled voice remixing feature for changing timbre, pitch, pace and accent. Both models support multi-speaker dialogue, extended audio generation and non-verbal markers such as <laughs>, <sigh> and <gasp>.

On Hume AI evaluations, Gemini 3.8 Flash TTS scored 71.4 overall and 60.8 for accent modelling. It ranked first in Hume’s Overall Quality Index, with Flash-Lite TTS in second place. Voice cloning requires identity verification, a 30-second reference recording and explicit consent. Generated files include SynthID watermarks and C2PA metadata. The models are available through Google AI Studio and the Gemini API, with integrations including Figma, HeyGen and Vercel.

Written by Sakhanda Wire AI from reporting by AI News. Facts, quotes and full context are in the original article below.

Originally published by AI News on

Read the original on AI News ↗

The reporting and the image belong to AI News and are credited and linked above; the text on this page is Sakhanda Wire's own summary.

← Back to the news

More stories

All the latest news